Spaces:
Paused
Paused
Create test_single_wav.py
Browse files- stt/test_single_wav.py +71 -0
stt/test_single_wav.py
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python3
|
| 2 |
+
"""
|
| 3 |
+
Single WAV file tester
|
| 4 |
+
Usage: python test_single_wav.py <wav_file>
|
| 5 |
+
"""
|
| 6 |
+
import sys
|
| 7 |
+
import wave
|
| 8 |
+
from google.cloud import speech
|
| 9 |
+
|
| 10 |
+
def test_wav_file(wav_file_path):
|
| 11 |
+
try:
|
| 12 |
+
print(f"Testing WAV file: {wav_file_path}")
|
| 13 |
+
|
| 14 |
+
# Read WAV file
|
| 15 |
+
with wave.open(wav_file_path, 'rb') as wav_file:
|
| 16 |
+
n_channels = wav_file.getnchannels()
|
| 17 |
+
sample_width = wav_file.getsampwidth()
|
| 18 |
+
sample_rate = wav_file.getframerate()
|
| 19 |
+
n_frames = wav_file.getnframes()
|
| 20 |
+
wav_audio = wav_file.readframes(n_frames)
|
| 21 |
+
|
| 22 |
+
print(f"WAV Info: {n_channels}ch, {sample_width*8}bit, {sample_rate}Hz, {n_frames} frames, {n_frames/sample_rate:.2f}s")
|
| 23 |
+
|
| 24 |
+
# Google STT client
|
| 25 |
+
credentials_path = "./credentials/google-service-account.json"
|
| 26 |
+
client = speech.SpeechClient.from_service_account_file(credentials_path)
|
| 27 |
+
|
| 28 |
+
# Config
|
| 29 |
+
config = speech.RecognitionConfig(
|
| 30 |
+
encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
|
| 31 |
+
sample_rate_hertz=sample_rate,
|
| 32 |
+
language_code="tr-TR",
|
| 33 |
+
audio_channel_count=n_channels,
|
| 34 |
+
enable_separate_recognition_per_channel=False,
|
| 35 |
+
)
|
| 36 |
+
|
| 37 |
+
# Audio
|
| 38 |
+
audio = speech.RecognitionAudio(content=wav_audio)
|
| 39 |
+
|
| 40 |
+
# Recognize
|
| 41 |
+
print("Sending to Google API...")
|
| 42 |
+
response = client.recognize(config=config, audio=audio)
|
| 43 |
+
|
| 44 |
+
print(f"Response: {response}")
|
| 45 |
+
print(f"Results count: {len(response.results)}")
|
| 46 |
+
|
| 47 |
+
if response.results:
|
| 48 |
+
for i, result in enumerate(response.results):
|
| 49 |
+
print(f"Result {i}: {result}")
|
| 50 |
+
if result.alternatives:
|
| 51 |
+
print(f" Transcript: '{result.alternatives[0].transcript}'")
|
| 52 |
+
print(f" Confidence: {result.alternatives[0].confidence}")
|
| 53 |
+
return True
|
| 54 |
+
else:
|
| 55 |
+
print("No results returned")
|
| 56 |
+
return False
|
| 57 |
+
|
| 58 |
+
except Exception as e:
|
| 59 |
+
print(f"Error: {e}")
|
| 60 |
+
import traceback
|
| 61 |
+
traceback.print_exc()
|
| 62 |
+
return False
|
| 63 |
+
|
| 64 |
+
if __name__ == "__main__":
|
| 65 |
+
if len(sys.argv) != 2:
|
| 66 |
+
print("Usage: python test_single_wav.py <wav_file>")
|
| 67 |
+
sys.exit(1)
|
| 68 |
+
|
| 69 |
+
wav_file = sys.argv[1]
|
| 70 |
+
success = test_wav_file(wav_file)
|
| 71 |
+
sys.exit(0 if success else 1)
|